Statistics Solutions

Video Tutorial: One Within One Between ANOVA

James Lani — Mon, 20 May 2013 16:04:10 +0000

The video below demonstrates how to conduct a one within one between ANOVA.

The post Video Tutorial: One Within One Between ANOVA appeared first on Statistics Solutions.

Reliability and Validity

James Lani — Thu, 16 May 2013 17:57:26 +0000

Reliability and validity are important aspects of selecting a survey instrument. Reliability refers to the extent that the instrument yields the same results over multiple trials. Validity refers to the extent that the instrument measures what it was designed to measure. In research, there are three ways to approach validity and they include content validity, construct validity, and criterion-related validity.

Content validity measures the extent to which the items that comprise the scale accurately represent or measure the information that is being assessed. Are the questions that are asked representative of the possible questions that could be asked?

Construct validity measures what the calculated scores mean and if they can be generalized. Construct validity uses statistical analyses, such as correlations, to verify the relevance of the questions. Questions from an existing, similar instrument, that has been found reliable, can be correlated with questions from the instrument under examination to determine if construct validity is present. If the scores are highly correlated it is called convergent validity. If convergent validity exists, construct validity is supported.

Criterion-related validity has to do with how well the scores from the instrument predict a known outcome they are expected to predict. Statistical analyses, such as correlations, are used to determine if criterion-related validity exists. Scores from the instrument in question should be correlated with an item they are known to predict. If a correlation of > .60 exists, criterion related validity exists as well.

Reliability can be assessed with the test-retest method, alternative form method, internal consistency method, the split-halves method, and inter-rater reliability.

Test-retest is a method that administers the same instrument to the same sample at two different points in time, perhaps one year intervals. If the scores at both time periods are highly correlated, > .60, they can be considered reliable. The alternative form method requires two different instruments consisting of similar content. The same sample must take both instruments and the scores from both instruments must be correlated. If the correlations are high, the instrument is considered reliable. Internal consistency uses one instrument administered only once. The coefficient alpha (or Cronbach’s alpha) is used to assess the internal consistency of the item. If the alpha value is .70 or higher, the instrument is considered reliable. The split-halves method also requires one test administered once. The number of items in the scale are divided into halves and a correlation is taken to estimate the reliability of each half of the test. To estimate the reliability of the entire survey, the Spearman-Brown correction must be applied. Inter-rater reliability involves comparing the observations of two or more individuals and assessing the agreement of the observations. Kappa values can be calculated in this instance.

The post Reliability and Validity appeared first on Statistics Solutions.

Video Tutorial: SEM Assumptions

James Lani — Thu, 02 May 2013 14:39:38 +0000

The post Video Tutorial: SEM Assumptions appeared first on Statistics Solutions.

Video Tutorial: Two Between ANOVA

James Lani — Thu, 02 May 2013 14:34:17 +0000

The post Video Tutorial: Two Between ANOVA appeared first on Statistics Solutions.

Video Tutorial: One Within One Between ANOVA

James Lani — Thu, 02 May 2013 14:26:14 +0000

The post Video Tutorial: One Within One Between ANOVA appeared first on Statistics Solutions.

Selecting a Survey Instrument

James Lani — Wed, 10 Apr 2013 20:06:00 +0000

When selecting a survey instrument for dissertation research, there are some important factors that should influence the decision. First, and foremost, the instrument should accurately measure the variable of interest. If the goal of research is to assess job satisfaction of top executives at fortune 500 companies, you will need to select an instrument that measures job satisfaction. In this instance, the Job Satisfaction Survey would be a good choice. The instrument is composed of 36 Likert scale items. In the case of this particular instrument, you can calculate a total score, or you calculate nine sub-scale scores. If you want to know about overall job satisfaction, the total score would be a sufficient measure.

It is important to select an instrument that has been found to be reliable and valid. Reliability refers to the extent that the instrument yields the same results over multiple trials. Validity refers to the extent that the instrument measures what it was designed to measure. There are several ways to assess the reliability and validity of the instrument once data has been collected however, these factors are important to know prior to data collection. To determine if the instrument has been proven reliable and valid, it is important to research the instrument and find out what previous studies ascertained. A quick assessment of previous research that used the instrument should allow you to do this.

When selecting a survey instrument, it is important to know how total scores or averages are calculated and what higher or lower scores indicate. Oftentimes, in survey instruments, the tool can be comprised of negatively worded items as well as positively worded items. When scoring these instruments, it is important to know which items need to be reverse scored prior to calculation. It is important to understand how the instrument has been scored in previous studies and to duplicate that scoring method for your study.

One other factor to consider when selecting an instrument is the type of data you will be obtain. If you are planning to use a simply descriptive study, the design of the response options can vary from question to question. If you plan to use inferential statistics, it is beneficial to be able to create total scores. In order to create total scores or average scores, you typically want all response options that make up a particular scale or sub-scale to have the same range, perhaps 1 – 5 where 1 = strongly disagree and 5 = strongly agree.

Remember, the two most important factors in selecting an instrument are that the instrument measures your variable of interest and that it is reliable and valid. That information coupled with the other suggestions will assist you in the selection of an excellent instrument.

The post Selecting a Survey Instrument appeared first on Statistics Solutions.

Video Tutorial: One-Way ANOVA

James Lani — Wed, 10 Apr 2013 19:47:00 +0000

The video below demonstrates how to conduct a One-Way ANOVA:

The post Video Tutorial: One-Way ANOVA appeared first on Statistics Solutions.

Video Tutorial: MPlus Data Setup

James Lani — Mon, 08 Apr 2013 19:11:00 +0000

The post Video Tutorial: MPlus Data Setup appeared first on Statistics Solutions.

Univariate and Multivariate Outliers

James Lani — Mon, 08 Apr 2013 17:02:00 +0000

A univariate outlier is a data point that consists of an extreme value on one variable. A multivariate outlier is a combination of unusual scores on at least two variables. Both types of outliers can influence the outcome of statistical analyses. Outliers exist for four reasons. Incorrect data entry can cause data to contain extreme cases. A second reason for outliers can be failure to indicate codes for missing values in a dataset. Another possibility is that the case did not come from the intended sample. And finally, the distribution of the sample for specific variables may have a more extreme distribution than normal.

In many parametric statistics, univariate and multivariate outliers must be removed from the dataset. When looking for univariate outliers for continuous variables, standardized values (z scores) can be used. If the statistical analysis to be performed does not contain a grouping variable, such as linear regression, canonical correlation, or SEM among others, then the data set should be assessed for outliers as a whole. If the analysis to be conducted does contain a grouping variable, such as MANOVA, ANOVA, ANCOVA, or logistic regression, among others, then data should be assessed for outliers separately within each group. For continuous variables, univariate outliers can be considered standardized cases that are outside the absolute value of 3.29. However, caution must be taken with extremely large sample sizes, as outliers are expected in these datasets. Once univariate outliers have been removed from a dataset, multivariate outliers can be assessed for and removed.

Multivariate outliers can be identified with the use of Mahalanobis distance, which is the distance of a data point from the calculated centroid of the other cases where the centroid is calculated as the intersection of the mean of the variables being assessed. Each point is recognized as an X, Y combination and multivariate outliers lie a given distance from the other cases. The distances are interpreted using a p < .001 and the corresponding χ² value with the degrees of freedom equal to the number of variables. Multivariate outliers can also be recognized using leverage, discrepancy, and influence. Leverage is related to Mahalanobis distance but is measured on a different scale so that the χ²distribution does not apply. Large scores indicate the case if further out however may still lie on the same line. Discrepancy assesses the extent that the case is in line with the other cases. Influence is determined by leverage and discrepancy and assesses changes in coefficients when cases are removed. Cases > 1.00 are likely to be considered outliers.

The post Univariate and Multivariate Outliers appeared first on Statistics Solutions.

Video Tutorial: One Sample t Test

James Lani — Mon, 08 Apr 2013 16:54:00 +0000

The video below demonstrates how to conduct a one sample t test:

The post Video Tutorial: One Sample t Test appeared first on Statistics Solutions.