1.5 Choice of Statistical Techniques

As mentioned earlier, the choice of a statistical technique is a complex issue, which should not be reduced to a cookbook approach. With this caveat, we have suggested appropriate techniques for different data analysis situations in Tables 1 and 2. They are meant to be a framework, and are intended as general guidelines. They should not be applied rigidly in all situations. It would be desirable to try more than one way of analyzing the data, whenever possible.

Table 1:
Appropriate techniques for problems without distinction between independent and dependent variables

No. of Variables

Measurement Level

Analysis Method

NON-METRIC

One

Nominal

Frequencies, Proportions

One

Ordinal

Median, Mode

One

Preferences

Rank Consensus among evaluators

METRIC

One

Interval or ratio scale

Mean, Median, Mode, Variance, Skewness, Kurtosis

NON-METRIC

Two

Dichotomous

Cross-tabulation Chi-square

Two

Nominal

Cross tabulation, Chi-square, Correspondence Analysis

Two

Ordinal

Kendall's Tau,Spearman's Rho, Gamma

METRIC

Two

Interval-scale

Scatter plot, Pearson's Correlation Coefficient

More than two

Interval-scale

Principal Components Analysis, Factor Analysis, Cluster Analysis Multidimensional Scaling

 

Table 2:
Appropriate techniques for problems with distinction between independent and dependent variables

No. of Variables

Measurement Level

Analysis Method

Dependent

Independent

Dependent

Independent

 

One

One

Nominal

Nominal

Non-parametric tests, Chi-square

One

One

Nominal (dichotomous)

Nominal

Multiple Classification Analysis

One

One

Nominal

Nominal (Dichotomous)

Wilcoxon's two sample test, Chi-square, Kolmogorov-Smirnov Test

One

One

Interval-scale

Nominal (Dichotomous)

t-test,  Analysis of Variance

One

One

Interval-scale

Interval-scale

Regression Analysis

One

One

Interval-scale

Nominal

Analysis of Variance

One

More

Nominal

Interval-scale

Discriminant Analysis

One

More

Interval-scale

Nominal

Analysis of Variance, Multiple Regression Analysis, Multiple Classification Analysis

One

More

Interval scale

Dummy

Analysis of Variance, Multiple Regression Analysis, Multiple Classification Analysis

One

More

Interval-scale

Interval-scale

Multiple Regression Analysis